OWASP Top 10 for Agentic Applications
OWASP GenAI Security Project list of the ten most critical risks for AI agents and agentic systems
Ten risk categories specific to agents (agent goal hijack, tool misuse, identity and privilege abuse, supply-chain and memory poisoning, cascading failures, insecure inter-agent communication, rogue agents and others) with mitigations, the agentic successor to the LLM Top 10.
Contribute
Spot an error, or know a record we should add? Members can propose additions and submit corrections.